CN112412444A

CN112412444A - Injection-production communication strength determination method and device, computer equipment and storage medium

Info

Publication number: CN112412444A
Application number: CN202011314804.0A
Authority: CN
Inventors: 孙琦; 倪天禄; 徐思远; 王晴; 李海甫; 王艳丽; 孙海燕; 李博文; 郭振; 王娜娜
Original assignee: Petrochina Co Ltd
Current assignee: Petrochina Co Ltd
Priority date: 2020-11-20
Filing date: 2020-11-20
Publication date: 2021-02-26
Anticipated expiration: 2040-11-20
Also published as: CN112412444B

Abstract

The application discloses a method and a device for determining injection-production communication strength, computer equipment and a storage medium, and belongs to the field of oil exploitation. In the embodiment of the application, the oil recovery amount-oil recovery time series of a plurality of water injection layers in the water injection well and the oil recovery amount-oil recovery time series of a plurality of oil recovery layers in the oil recovery well can be directly obtained through the water injection amount splitting model and the oil recovery amount splitting model. Based on the similarity between the oil recovery-oil recovery time series of the water injection layers and the oil recovery-oil recovery time series of the oil production layers, the injection-oil recovery communication strength between the water injection layers and the oil production layers can be quickly obtained. Through the technical scheme, the process of determining the injection-production communication strength does not need to be stopped, complex operation and extra construction operation are not needed, the efficiency of determining the injection-production communication strength is high, and the cost is low.

Description

Injection-production communication strength determination method and device, computer equipment and storage medium

Technical Field

The application relates to the field of oil exploitation, in particular to a method and a device for determining injection-production communication strength, computer equipment and a storage medium.

Background

The injection-production communication strength refers to the communication condition between a water injection well and a production well in a water-drive oil reservoir. In the actual production of oil fields, the injection-production communication condition is a very important problem which is difficult to determine. The accurate judgment of the injection-production communication condition can provide a basis for the description of the distribution of the residual oil and the formulation of an oil field development scheme, has a certain guiding function on the production adjustment and oil and water stabilization of the oil field, and has an important significance on the improvement of the recovery ratio of the crude oil of the water-drive oil reservoir.

In the related technology, the main research on the injection-production communication conditions include tracer testing, multi-well testing analysis, geochemical methods and the like, the methods are often complex in operation and need additional construction operation, normal production operation of an oil field can be influenced in the implementation process, and the efficiency for determining the injection-production communication strength is low.

Disclosure of Invention

The embodiment of the application provides a method and a device for determining injection-production communication strength, computer equipment and a storage medium, and the efficiency of determining the injection-production communication strength can be improved. The technical scheme is as follows:

in one aspect, a method for determining injection-production communication strength is provided, and the method includes:

acquiring a water injection amount-water injection time sequence of a water injection well and an oil recovery amount-oil recovery time sequence of an oil recovery well;

inputting the water injection quantity-water injection time sequence of the water injection well and the permeability of each water injection layer in the water injection well into a water injection quantity splitting model, and outputting the water injection quantity-water injection time sequence of each water injection layer by the water injection quantity splitting model, wherein the water injection quantity splitting model is obtained by training according to the water injection quantity-water injection time sequence of at least one sample water injection well, the sample water injection quantity-water injection time sequence and the sample permeability of each sample water injection layer in the at least one sample water injection well;

inputting the oil recovery amount-oil recovery time sequence of the oil recovery well and the permeability of each oil recovery layer in the oil recovery well into an oil recovery amount splitting model, and outputting the oil recovery amount-oil recovery time sequence of each oil recovery layer by the oil recovery amount splitting model, wherein the oil recovery amount splitting model is obtained by training according to the oil recovery amount-oil recovery time sequence of at least one sample oil recovery well, the sample oil recovery amount-oil recovery time sequence of each sample oil recovery layer in the at least one sample oil recovery well and the sample permeability;

inputting the water injection quantity-water injection time sequence of each water injection layer and the oil recovery quantity-oil recovery time sequence of each oil production layer into a correlation determination model, and outputting a correlation coefficient between the water injection quantity-water injection time sequence of each water injection layer and the oil recovery quantity-oil recovery time sequence of each oil production layer through the correlation determination model;

and determining the injection-production communication strength between each water injection layer and each oil production layer based on the correlation coefficient.

In one possible embodiment, the inputting the water injection amount-water injection time series of the water injection well and the permeability of each water injection layer in the water injection well into a water injection amount splitting model, and the outputting the water injection amount-water injection time series of each water injection layer by the water injection amount splitting model includes:

inputting the water injection quantity-water injection time sequence of the water injection well and the permeability of each water injection layer in the water injection well into a water injection quantity splitting model, and obtaining a first seepage range of each water injection layer based on the permeability of each water injection layer through the water injection quantity splitting model, wherein the first seepage range is a ratio of the permeability of each water injection layer to the highest permeability of each water injection layer;

obtaining the water injection distribution proportion of each water injection layer based on the permeability of each water injection layer and the seepage pole difference of each water injection layer through the water injection amount splitting model;

and obtaining the water injection quantity-water injection time sequence of each water injection layer based on the water injection distribution proportion and the water injection quantity-water injection time sequence of the water injection well.

In one possible embodiment, the inputting the oil recovery-oil recovery time series of the oil production well and the permeability of each oil production zone in the oil production well into a production split model, and the outputting the oil recovery-oil recovery time series of each oil production zone by the production split model includes:

inputting the oil production amount-oil production time sequence of the oil production well and the permeability of each oil production layer in the oil production well into an oil production amount splitting model, and obtaining a second seepage extreme difference of each oil production layer based on the permeability of each oil production layer through the oil production amount splitting model, wherein the second seepage extreme difference is a ratio of the permeability of each oil production layer to the highest permeability of each oil production layer;

obtaining the oil output proportion of each oil production layer based on the permeability of each oil production layer and the seepage pole difference of each oil production layer through the oil production split model;

and obtaining the oil recovery amount-oil recovery time sequence of each oil recovery layer based on the oil production ratio and the oil recovery amount-oil recovery time sequence of the oil recovery well.

In a possible embodiment, the inputting the water injection amount-water injection time series of each water injection layer and the oil production amount-oil production time series of each oil production layer into a correlation determination model, and the outputting, by the correlation determination model, a correlation coefficient between the water injection amount-water injection time series of each water injection layer and the oil production amount-oil production time series of each oil production layer includes:

inputting the water injection amount-water injection time sequence of each water injection layer and the oil recovery amount-oil recovery time sequence of each oil recovery layer into a correlation determination model, and acquiring a water injection amount-oil recovery amount difference matrix between each water injection layer and each oil recovery layer through the correlation determination model, wherein the numerical value in the water injection amount-oil recovery amount difference matrix is the difference value between the water injection amount of each water injection layer and the oil recovery amount of each oil recovery layer;

and obtaining a correlation coefficient between the water injection quantity-water injection time sequence of each water injection layer and the oil recovery-oil recovery time sequence of each oil recovery layer through the correlation determination model based on the water injection quantity-oil recovery difference matrix.

In a possible embodiment, the obtaining, by the correlation determination model, a correlation coefficient between the water injection amount-water injection time series of each water injection layer and the oil production amount-oil production time series of each oil production layer based on the water injection amount-oil production amount difference matrix includes:

obtaining a target path by taking the upper left corner of the water injection quantity-oil production quantity difference matrix as a starting point and the lower right corner of the water injection quantity-oil production quantity difference matrix as an end point through the correlation determination model, wherein the target path is a path with the minimum sum of the passed numerical values;

and determining the sum of the numerical values passed by the target path as the correlation coefficient.

In a possible embodiment, the determining, based on the correlation coefficient, the injection-production communication strength between the respective water injection layer and the respective oil production layer includes:

and carrying out normalization processing on the correlation coefficient, and determining the injection-production communication strength between each water injection layer and each oil production layer.

In one possible embodiment, the distance between the water injection well and the production well is less than or equal to a distance threshold.

In one aspect, an injection-production communication strength determination apparatus is provided, the apparatus including:

the acquisition module is used for acquiring a water injection quantity-water injection time sequence of the water injection well and an oil recovery quantity-oil recovery time sequence of the oil recovery well;

the water injection rate splitting model is obtained by training the water injection rate-water injection time sequence of at least one sample water injection well, the sample water injection rate-water injection time sequence and the sample permeability of each sample water injection layer in the at least one sample water injection well;

a second input module, configured to input the oil recovery-oil recovery time series of the oil recovery well and the permeability of each oil recovery layer in the oil recovery well into a volume splitting model, and output the oil recovery-oil recovery time series of each oil recovery layer by the volume splitting model, where the volume splitting model is obtained by training according to the oil recovery-oil recovery time series of at least one sample oil recovery well, and the sample oil recovery-oil recovery time series and the sample permeability of each sample oil recovery layer in the at least one sample oil recovery well;

a third input module, configured to input the water injection amount-water injection time series of each water injection layer and the oil recovery amount-oil recovery time series of each oil recovery layer into a correlation determination model, and output a correlation coefficient between the water injection amount-water injection time series of each water injection layer and the oil recovery amount-oil recovery time series of each oil recovery layer through the correlation determination model;

and the injection-production communication strength determining module is used for determining the injection-production communication strength between each water injection layer and each oil production layer based on the correlation coefficient.

In a possible embodiment, the first input module is configured to input the water injection amount-water injection time series of the water injection well and the permeability of each water injection layer in the water injection well into a water injection amount splitting model, and obtain, through the water injection amount splitting model, a first seepage range of each water injection layer based on the permeability of each water injection layer, where the first seepage range is a ratio between the permeability of each water injection layer and the highest permeability of each water injection layer; obtaining the water injection distribution proportion of each water injection layer based on the permeability of each water injection layer and the seepage pole difference of each water injection layer through the water injection amount splitting model; and obtaining the water injection quantity-water injection time sequence of each water injection layer based on the water injection distribution proportion and the water injection quantity-water injection time sequence of the water injection well.

In a possible implementation manner, the second input module is configured to input the oil recovery-oil recovery time series of the oil recovery well and the permeability of each oil recovery layer in the oil recovery well into an oil recovery splitting model, and obtain, through the oil recovery splitting model, a second seepage range of each oil recovery layer based on the permeability of each oil recovery layer, where the second seepage range is a ratio between the permeability of each oil recovery layer and the highest permeability of each oil recovery layer; obtaining the oil output proportion of each oil production layer based on the permeability of each oil production layer and the seepage pole difference of each oil production layer through the oil production split model; and obtaining the oil recovery amount-oil recovery time sequence of each oil recovery layer based on the oil production ratio and the oil recovery amount-oil recovery time sequence of the oil recovery well.

In a possible implementation manner, the third input module is configured to input the water injection amount-water injection time series of each water injection layer and the oil recovery amount-oil recovery time series of each oil recovery layer into a correlation determination model, and obtain a water injection amount-oil recovery amount difference matrix between each water injection layer and each oil recovery layer through the correlation determination model, where a numerical value in the water injection amount-oil recovery amount difference matrix is a difference between the water injection amount of each water injection layer and the oil recovery amount of each oil recovery layer; and obtaining a correlation coefficient between the water injection quantity-water injection time sequence of each water injection layer and the oil recovery-oil recovery time sequence of each oil recovery layer through the correlation determination model based on the water injection quantity-oil recovery difference matrix.

In a possible implementation manner, the third input module is configured to obtain, through the correlation determination model, a target path with an upper left corner of the water injection amount-oil production amount difference matrix as a starting point and a lower right corner of the water injection amount-oil production amount difference matrix as an end point, where the target path is a path with a minimum sum of passed numerical values; and determining the sum of the numerical values passed by the target path as the correlation coefficient.

In a possible implementation manner, the injection-production communication strength determining module is configured to perform normalization processing on the correlation coefficient, and determine the injection-production communication strength between each water injection layer and each oil production layer.

In one aspect, a computer apparatus is provided that includes one or more processors and one or more memories having at least one program code stored therein, the program code being loaded and executed by the one or more processors to implement the voidage replacement connectivity strength determination method.

In one aspect, a computer-readable storage medium having at least one program code stored therein is provided, the program code being loaded and executed by a processor to implement the voidage replacement (egl) connectivity strength determining method.

In the embodiment of the application, the oil recovery amount-oil recovery time series of a plurality of water injection layers in the water injection well and the oil recovery amount-oil recovery time series of a plurality of oil recovery layers in the oil recovery well can be directly obtained through the water injection amount splitting model and the oil recovery amount splitting model. Based on the similarity between the oil recovery-oil recovery time series of the water injection layers and the oil recovery-oil recovery time series of the oil production layers, the injection-oil recovery communication strength between the water injection layers and the oil production layers can be quickly obtained. Through the technical scheme, the process of determining the injection-production communication strength does not need to be stopped, complex operation and extra construction operation are not needed, the efficiency of determining the injection-production communication strength is high, and the cost is low.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a method for determining injection-production communication strength according to an embodiment of the present disclosure;

fig. 2 is a flowchart of a method for determining injection-production communication strength according to an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of an injection-production communication strength determination apparatus according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

In the embodiment of the present application, a water injection amount splitting model and an oil production amount splitting model are involved, and in order to describe the embodiment of the present application more clearly, a training method of the water injection amount splitting model and the oil production amount splitting model is described first. In addition, when training the water injection amount splitting model and the oil recovery amount splitting model, a terminal can be used as an execution subject, and a server can be used as an execution subject.

In one possible implementation, the training of the water injection split model by the terminal includes two processes, i.e., sample preparation and model training, which will be described separately below.

In the sample preparation process, the terminal can collect a sample injection amount-water injection time series of the sample injection well, a sample injection amount-water injection time series of each sample water injection layer in the sample injection well, and a permeability of each sample water injection layer, optionally, the number of the sample injection wells is plural, and only one sample injection well is taken as an example for description below.

For the sample water injection amount-water injection time sequence of the sample water injection well, the terminal can obtain the sample water injection amounts of the sample water injection well at different times, and arrange the obtained sample water injection amounts according to the time corresponding to the sample water injection amounts to obtain the sample water injection amount-water injection amount time sequence of the sample water injection well. For example, for a sample injection well, the terminal obtains 100m injection amount of 5 samples in the same day³/min、80m³/min、90m³/min、105m³Min and 95m³Min, and at the same time, the water injection rate of 5 samples is 100m³/min、80m³/min、90m³/min、105m³Min and 95m³The times per min correspond to 8: 20. 9: 20. 10: 20. 11: 20 and 12: the terminal is able to obtain a sample injection-injection time series for the sample injection well (100, 80, 90, 105, 95).

The terminal can be obtained in any of the following ways for a sample fill rate-fill time sequence for each sample fill layer in a sample fill well.

Mode 1, in the process of injecting water into a sample water injection well, a technician adds isotopes into the injected water, measures the radioactive intensity of each sample water injection layer in the sample water injection well after the isotopes are injected through radioactive intensity measuring equipment, and sends the measured radioactive intensity to a terminal. And the terminal obtains a sample water injection amount-water injection time sequence of each sample water injection layer according to the radioactivity intensity.

For example, if the terminal obtains a sample injection-injection time sequence for the sample injection well as (100, 80, 90, 105, 95). The sample water injection well comprises two sample water injection layers, wherein the corresponding radioactive intensity of one sample water injection layer is 2 Becker (Bq), the corresponding radioactive intensity of the other sample water injection layer is 3Bq, and the terminal can determine the water absorption ratio of the two sample water injection layers according to the corresponding radioactive intensities of the two sample water injection layers respectively, namely, the water absorption ratio of one sample water injection layer is 2/(2+3) ═ 0.4, and the water absorption ratio of the other sample water injection layer is 3/(2+3) ═ 0.6. The terminal obtains the sample water injection amount-water injection amount time sequence of one sample water injection layer as (40, 32, 36, 42, 38) and the sample water injection amount-water injection amount time sequence of the other sample water injection layer as (60, 48, 54, 63, 57) according to the water absorption ratios of the two sample water injection layers of 0.4 and 0.6 and the sample water injection amount-water injection amount time sequence of the sample water injection well as the sample water injection amount-water injection amount time sequence of the sample water injection well (100, 80, 90, 105, 95).

Mode 2, a technician can put a turbine flowmeter with a positioning device into the sample water injection well, and the turbine flowmeter with the positioning device can communicate with a terminal. The terminal can determine the current position of the turbine flowmeter through the positioning device, and the measured sample water injection layer is determined according to the position of the turbine flowmeter. The terminal can obtain the flow rate of water in each sample water injection layer through a turbine flowmeter. The terminal can obtain the sample water injection amount-water injection amount time sequence of each sample water injection layer based on the flow rate of water in each sample water injection layer and the cross-sectional area of the sample water injection layer.

For the permeability of each sample water injection layer, the terminal can determine the rock stratum type corresponding to each sample water injection layer according to the logging curve. And the terminal acquires the permeability corresponding to each sample water injection layer based on the rock stratum type corresponding to each sample water injection layer. Of course, the permeability corresponding to the formation type may be input in advance by a technician, or may be obtained by a terminal from a server, which is not limited in this embodiment of the application.

In the model training process, the terminal can input the sample water injection amount-water injection amount time sequence of the sample water injection well and the permeability of each sample water injection layer into the first model, and the first model predicts based on the permeability of each sample water injection layer to obtain the predicted water absorption ratio corresponding to each sample water injection layer. And the terminal outputs the predicted water injection amount-water injection amount time sequence of each sample water injection layer through the first model based on the sample water injection amount-water injection amount time sequence of the sample water injection well and the corresponding predicted water absorption ratio of each sample water injection layer. And the terminal adjusts the model parameters of the first model according to the difference information between the predicted water injection amount-water injection amount time sequence of each sample water injection layer and the sample water injection amount-water injection amount time sequence of each sample water injection layer until the loss function of the first model converges to the target function value or the iteration times of the first model reach the target times, and stops training the first model. The terminal obtains the first model at this time as a water injection split model, wherein the objective function value and the objective times are set by a technician according to actual conditions, and the embodiment of the application does not limit the objective function value and the objective times.

It should be noted that the water injection splitting model can be selected from Linear Regression (Linear Regression), Logistic Regression (Logistic Regression), Linear Discriminant Analysis (Linear Discriminant Analysis), Classification and Regression tree model (Classification and Regression Trees), naive bayes (na

Bayes), K-Nearest Neighbors (K-Nearest Neighbors), Learning Vector Quantization (Learning Vector Quantization), Support Vector Machines (Support vectors Machines), Random Forest (Random Forest) and other models, which are not limited in the embodiment of the present application.

Optionally, the terminal may also be configured to train the two or more models simultaneously based on sample data obtained in the sample preparation process, and the terminal may be configured to test the trained multiple models, and determine, from the multiple models, a model with a best water injection splitting effect as a water injection splitting model in a subsequent use process, where the water injection splitting effect preferably indicates that a similarity between a predicted water injection-water injection time sequence of each sample water injection layer predicted by the model and a sample water injection-water injection time sequence of each sample water injection layer is highest.

For example, if the sample fill rate-fill time series of each of the sample fill layers of the 100 sample wells and the 100 sample wells are obtained as training samples in the data preparation process, the terminal can use the sample fill rate-fill time series of each of the sample fill layers of the 80 sample wells and the sample wells as a training set, and use the sample fill rate-fill time series of each of the remaining 20 sample wells and the sample fill layers of the sample wells as a test set. The terminal trains three models based on the training set, which are respectively recorded as model A, model B and model C. The terminal can adopt the test set to respectively test the model A, the model B and the model C, and the similarity between the predicted water injection quantity-water injection time sequence of each sample water injection layer output by the model A, the model B and the model C and the sample water injection quantity-water injection time sequence of each sample water injection layer is obtained. And the terminal determines the model with the highest similarity as a water injection split model. Alternatively, the terminal can determine the similarity between the predicted water injection amount-water injection time series of each sample water injection layer and the sample water injection amount-water injection time series of each sample water injection layer by calculating the euclidean distance between the two series.

Under the embodiment, the terminal can determine the model with the best water injection splitting effect from the various models as the water injection splitting model, and can achieve better water injection splitting effect in the subsequent process of splitting the water injection of the water injection well by adopting the water injection splitting model.

In one possible implementation, the training of the oil recovery split model by the terminal includes two processes, sample preparation and model training, which will be described separately below.

In the sample preparation process, the terminal can collect a sample oil recovery-oil recovery time series of a sample oil recovery well, a sample oil recovery-oil recovery time series of each sample oil recovery layer in the sample oil recovery well, and a permeability of each sample oil recovery layer, optionally, the number of the sample oil recovery wells is plural, and only one sample oil recovery well is taken as an example for description.

Sample oil recovery for sample oil recovery well-at-time of oil recoveryIn the time sequence, the terminal can obtain the sample oil recovery quantities of the sample oil recovery wells at different times, and arrange the obtained sample oil recovery quantities according to the time corresponding to the sample oil recovery quantities to obtain the sample oil recovery quantity-oil recovery quantity time sequence of the sample oil recovery wells. For example, for a sample production well, the terminal has acquired 90m of 5 sample oil productions on the same day³/min、70m³/min、80m³/min、100m³Min and 90m³Min, simultaneously, 5 samples produced 90m³/min、70m³/min、80m³/min、100m³Min and 90m³The times per min correspond to 8: 20. 9: 20. 10: 20. 11: 20 and 12: the terminal is able to obtain a sample production-production time series (90, 70, 80, 100, 90) for the sample production well.

For example, a technician can place a turbine flow meter with a positioning device in the sample producing well, which can communicate with a terminal. The terminal can confirm the current measuring sample oil production layer of turbine flowmeter through positioner, just can obtain the velocity of flow of water at every sample oil production layer through turbine flowmeter. The terminal can obtain a sample oil recovery-oil recovery time sequence of each sample oil recovery layer based on the flow velocity of water in each sample oil recovery layer and the cross-sectional area of the sample oil recovery layer.

For the permeability of each sample oil production layer, the terminal can determine the rock stratum type corresponding to each sample oil production layer according to the logging curve. And the terminal acquires the permeability corresponding to each sample oil production layer based on the rock stratum type corresponding to each sample oil production layer.

In the model training process, the terminal can input the sample oil recovery-oil recovery time sequence of the sample oil recovery well and the permeability of each sample oil recovery layer into the second model, and the second model predicts the permeability of each sample oil recovery layer based on the permeability of each sample oil recovery layer to obtain the predicted oil recovery ratio corresponding to each sample oil recovery layer. And the terminal outputs the predicted oil recovery-oil recovery time sequence of each sample oil recovery layer through the second model based on the sample oil recovery-oil recovery time sequence of the sample oil recovery well and the predicted oil recovery proportion corresponding to each sample oil recovery layer. And the terminal adjusts the model parameters of the second model according to the difference information between the predicted oil production-oil production time sequence of each sample oil production layer and the sample oil production-oil production time sequence of each sample oil production layer until the loss function of the second model converges to the target function value or the iteration times of the second model reach the target times, and stops training the second model. And the terminal acquires the second model at the moment as an oil recovery split model.

It should be noted that the oil recovery splitting model may select Linear Regression (Linear Regression), Logistic Regression (Logistic Regression), Linear Discriminant Analysis (Linear Discriminant Analysis), Classification and Regression tree model (Classification and Regression Trees), Naive Bayes (Naive Bayes), K-Neighbors (K-Nearest Neighbors), Learning Vector Quantization (Learning Vector Quantization), Support Vector Machines (Support vectors), Random Forest (Bagging and Random Forest), and the like, which is not limited in the embodiment of the present application.

Optionally, the terminal may also be capable of simultaneously training the two or more models based on sample data obtained in the sample preparation process, and the terminal may be capable of testing the trained multiple models, and determine, from the multiple models, a model with a best oil recovery splitting effect as an oil recovery splitting model in a subsequent use process, where the oil recovery splitting effect is best when a similarity between a predicted oil recovery-oil recovery time sequence of each sample oil recovery layer predicted by the model and the sample oil recovery-oil recovery time sequence of each sample oil recovery layer is highest.

For example, if the sample oil recovery-oil recovery time series of each sample oil recovery layer in 100 sample oil recovery wells and 100 sample oil recovery wells are obtained as training samples in the data preparation process, the terminal can use the sample oil recovery-oil recovery time series of 80 sample oil recovery wells and each sample oil recovery layer in the sample oil recovery wells as a training set, and use the sample oil recovery-oil recovery time series of each sample oil recovery layer in the remaining 20 sample oil recovery wells and the sample oil recovery wells as a test set. The terminal trains three models based on the training set, and the three models are respectively recorded as a model D, a model E and a model F. The terminal can adopt the test set to respectively test the model D, the model E and the model F, and the similarity between the predicted oil recovery-oil recovery time sequence of each sample oil recovery layer output by the model D, the model E and the model F and the sample oil recovery-oil recovery time sequence of each sample oil recovery layer is obtained. And the terminal determines the model with the highest similarity as an oil recovery split model. Alternatively, the terminal can determine the similarity between the predicted oil recovery-oil recovery time series for each sample oil recovery layer and the sample oil recovery-oil recovery time series for each sample oil recovery layer by calculating the euclidean distance between the two sequences.

Under this kind of embodiment, the terminal can determine the best model of oil recovery volume split effect from the model of many types as oil recovery volume split model, in the in-process that adopts this oil recovery volume split model to split the oil recovery volume of oil recovery well in follow-up, can reach better oil recovery volume split effect.

It should be noted that the water injection amount splitting model and the oil recovery amount splitting model are the same or different types of models, and this is not limited in the embodiment of the present application.

Fig. 1 is a flowchart of a method for determining injection-production communication strength according to an embodiment of the present application, and referring to fig. 1, taking an execution subject as a terminal as an example, the method includes:

101. and the terminal acquires a water injection quantity-water injection time sequence of the water injection well and an oil recovery quantity-oil recovery time sequence of the oil recovery well.

102. And the terminal inputs the water injection amount-water injection time sequence of the water injection well and the permeability of each water injection layer in the water injection well into a water injection amount splitting model, and the water injection amount-water injection time sequence of each water injection layer is output by the water injection amount splitting model, wherein the water injection amount splitting model is obtained by training according to the water injection amount-water injection time sequence of at least one sample water injection well, the sample water injection amount-water injection time sequence of each sample water injection layer in at least one sample water injection well and the sample permeability.

103. And the terminal inputs the oil extraction amount-oil extraction time sequence of the oil extraction well and the permeability of each oil extraction layer in the oil extraction well into an oil extraction amount splitting model, and the oil extraction amount-oil extraction time sequence of each oil extraction layer is output by the oil extraction amount splitting model, wherein the oil extraction amount splitting model is obtained by training according to the oil extraction amount-oil extraction time sequence of at least one sample oil extraction well, the sample oil extraction amount-oil extraction time sequence of each sample oil extraction layer in at least one sample oil extraction well and the sample permeability.

104. And the terminal inputs the water injection amount-water injection time sequence of each water injection layer and the oil recovery amount-oil recovery time sequence of each oil production layer into a correlation determination model, and outputs a correlation coefficient between the water injection amount-water injection time sequence of each water injection layer and the oil recovery amount-oil recovery time sequence of each oil production layer through the correlation determination model.

105. And the terminal determines the injection-production communication strength between each water injection layer and each oil production layer based on the correlation coefficient.

In one possible embodiment, inputting the water injection amount-water injection time sequence of the water injection well and the permeability of each water injection layer in the water injection well into a water injection amount splitting model, and outputting the water injection amount-water injection time sequence of each water injection layer by the water injection amount splitting model comprises:

inputting the water injection quantity-water injection time sequence of the water injection well and the permeability of each water injection layer in the water injection well into a water injection quantity splitting model, and obtaining a first seepage range of each water injection layer based on the permeability of each water injection layer through the water injection quantity splitting model, wherein the first seepage range is the ratio of the permeability of each water injection layer to the highest permeability of each water injection layer.

And obtaining the water injection distribution proportion of each water injection layer based on the permeability of each water injection layer and the seepage range of each water injection layer through a water injection amount splitting model.

In one possible embodiment, inputting the oil recovery-oil recovery time series of the oil production well and the permeability of each oil production zone in the oil production well into a yield splitting model, and outputting the oil recovery-oil recovery time series of each oil production zone by the yield splitting model comprises:

and inputting the oil extraction amount-oil extraction time sequence of the oil extraction well and the permeability of each oil extraction layer in the oil extraction well into an oil extraction amount splitting model, and obtaining a second seepage range of each oil extraction layer based on the permeability of each oil extraction layer through the oil extraction amount splitting model, wherein the second seepage range is the ratio of the permeability of each oil extraction layer to the highest permeability of each oil extraction layer.

And obtaining the oil output proportion of each oil production layer based on the permeability of each oil production layer and the seepage pole difference of each oil production layer through an oil production split model.

And obtaining the oil recovery amount-oil recovery time sequence of each oil recovery layer based on the oil yield proportion and the oil recovery amount-oil recovery time sequence of the oil recovery well.

In one possible embodiment, inputting the water injection amount-water injection time series of each water injection layer and the oil production amount-oil production time series of each oil production layer into a correlation determination model, and outputting a correlation coefficient between the water injection amount-water injection time series of each water injection layer and the oil production amount-oil production time series of each oil production layer through the correlation determination model comprises:

inputting the water injection amount-water injection time sequence of each water injection layer and the oil recovery amount-oil recovery time sequence of each oil recovery layer into a correlation determination model, and acquiring a water injection amount-oil recovery difference matrix between each water injection layer and each oil recovery layer through the correlation determination model, wherein the numerical value in the water injection amount-oil recovery difference matrix is the difference value between the water injection amount of each water injection layer and the oil recovery amount of each oil recovery layer.

And obtaining a correlation coefficient between the water injection quantity-water injection time sequence of each water injection layer and the oil recovery quantity-oil recovery time sequence of each oil recovery layer through a correlation determination model based on the water injection quantity-oil recovery quantity difference matrix.

In one possible embodiment, obtaining a correlation coefficient between the water injection amount-water injection time series of each water injection layer and the oil production amount-oil production time series of each oil production layer based on the water injection amount-oil production amount difference matrix by the correlation determination model includes:

and obtaining a target path by taking the upper left corner of the water injection quantity-oil production quantity difference matrix as a starting point and the lower right corner of the water injection quantity-oil production quantity difference matrix as an end point through the correlation determination model, wherein the target path is the path with the minimum sum of the passed numerical values.

And determining the sum of the values passed by the target path as a correlation coefficient.

In one possible embodiment, determining the injection-production communication strength between each water injection layer and each oil production layer based on the correlation coefficient includes:

All the above optional technical solutions may be combined arbitrarily to form optional embodiments of the present application, and are not described herein again.

Fig. 2 is a flowchart of a method for determining injection-production communication strength according to an embodiment of the present application, and referring to fig. 2, taking an execution subject as a terminal as an example, the method includes:

201. and the terminal acquires a water injection quantity-water injection time sequence of the water injection well and an oil recovery quantity-oil recovery time sequence of the oil recovery well.

In a possible implementation mode, a water injection pump is installed on the water injection well, a water injection flow meter is installed on the water injection pump, and the water injection flow meter can acquire the water injection amount of water injected into the water injection well through the water injection pump in real time. The terminal can be connected with a water injection flowmeter installed on the water injection pump, and the water injection quantity of water injected to the water injection well by the water injection pump is obtained through the water injection flowmeter. And the terminal carries out water injection quantity of water injection to the water injection well based on the water injection pump to obtain a water injection quantity-water injection time sequence of the water injection well. Correspondingly, install the oil recovery pump on the oil recovery well, install the oil recovery flowmeter on the oil recovery pump, the oil recovery flowmeter can acquire the oil recovery volume of carrying out the oil recovery from the oil recovery well through the oil recovery pump in real time. The terminal can link to each other with the oil recovery flowmeter of installation on the oil recovery pump, obtains the oil recovery volume that the oil recovery pump carries out the oil recovery to the oil recovery well through the oil recovery flowmeter. And the terminal obtains the oil recovery amount-oil recovery time sequence of the oil recovery well based on the oil recovery amount of the oil recovery pump for recovering oil from the oil recovery well.

In a possible embodiment, the terminal can obtain from the server the water injection amount-water injection time series of the water injection wells and the oil production amount-oil production time series of the oil production wells, that is, each water injection well and each oil production well obtain data during the production process, which are collected and summarized by the server, and the terminal can directly obtain from the server the water injection amount-water injection time series of the water injection wells and the oil production amount-oil production time series of the oil production wells, wherein obtaining the data during the production process comprises: the position of each water injection well, the position of each oil production well, the water injection amount of each water injection well at different time, the oil production amount of each oil production well at different time, the permeability of each water injection layer in each water injection well, the permeability of each oil production layer in each oil production well and the like.

For example, during the production of a field, multiple injection and production wells are often drilled into the field. A field has a data collection facility for collecting and storing data associated with the production process. Technical personnel can number a plurality of water injection wells and a plurality of oil recovery wells respectively, and the numbers of the plurality of water injection wells and the plurality of oil recovery wells are recorded on the data collecting equipment. In addition, technicians can also guide the logging curves corresponding to the multiple water injection wells and the multiple oil production wells into the data collection equipment, so that the data can be managed uniformly. Of course, the water injection flow meter in the water injection pump installed on the water injection well can send the water injection amount collected in real time to the data collection device. The data collection equipment can bind the storage with the water injection well of corresponding serial number with the water injection volume, and correspondingly, the data collection equipment also can bind the storage with the oil recovery well of corresponding serial number with the oil recovery volume. The data collection equipment can send the stored related data to the server, the server stores the data, the server correspondingly maintains a database, and the database stores the related data on different oil fields. By the method, the safety of the related data can be improved, and the terminal can conveniently and quickly call the related data from the server. When a technician needs to process the related data of a certain oil field, the related data of the oil field can be quickly obtained through the terminal, namely, the technician inputs the identification of the oil field on the terminal, the terminal sends the identification of the oil field to the server, the server inquires in the correspondingly maintained database, and the related data corresponding to the identification of the oil field is sent to the terminal. And the terminal receives the relevant data sent by the server and acquires a water injection quantity-water injection time sequence of the water injection well and an oil recovery quantity-oil recovery time sequence of the oil recovery well from the relevant data.

In a possible embodiment, the distance between the water injection well and the oil production well is less than or equal to the distance threshold, that is to say, in this embodiment, the terminal is able to acquire only the water injection quantity-water injection time series and the oil production quantity-oil production time series from the eligible water injection well and oil production well. Because the relation of many to many often is between water injection well and the oil recovery well, also be that a water injection well probably to the intercommunication with many oil recovery wells, when carrying out the water injection in this oil recovery well, all can produce crude oil under the drive of water in the many oil recovery wells that correspond. And the production well that had both had the nearer with this mouthful of water injection well distance among the many oil recovery wells also exists in the oil recovery well that this mouthful of water injection well distance is far away, to the oil recovery well that is nearer with this mouthful of water injection well distance, when the water injection well carries out the water injection, the production well that is nearer can carry out quick response to the water of injecting into in the water injection well, just promptly is to produce crude oil under the drive of water. For the oil production well far away from the water injection well, when the water injection well injects water, the kinetic energy consumption of the water injected from the water injection well in the process of flowing in the stratum is high due to the long distance, and the crude oil in the oil production well far away cannot be effectively squeezed out, that is, the influence of the liquid injected into the water injection well on the crude oil production of the oil production well far away is small. Therefore, by limiting the distance between the water injection well and the oil production well, some oil production wells which are not strongly related to the water injection well can be eliminated, the data volume is reduced, the computing resources of the terminal are saved, and the computing efficiency is improved.

202. And (4) preprocessing the water injection quantity-water injection time sequence of the water injection well and the oil recovery quantity-oil recovery time sequence of the oil recovery well by the terminal.

In one possible embodiment, the terminal can preprocess a water injection amount-water injection time series of the water injection well and an oil recovery amount-oil recovery time series of the oil recovery well, and delete an abnormal water injection amount in the water injection amount-water injection time series and an abnormal oil recovery amount in the oil recovery amount-oil recovery time series to improve accuracy in determining the injection-oil recovery communication strength based on the water injection amount-water injection time series and the oil recovery amount-oil recovery time series.

For example, the technician can set a first water injection threshold, i.e. the maximum amount of water injected into the water injection well, and a first oil recovery threshold, i.e. the maximum amount of oil recovered from the oil recovery well, on the terminal. When any water injection amount larger than the first water injection amount threshold value exists in the water injection amount-water injection time series, the water injection amount is indicated to be an abnormal water injection amount, and the terminal can delete the water injection amount from the water injection amount-water injection time series. When any oil extraction amount larger than the first oil extraction amount threshold exists in the oil extraction amount-oil extraction time sequence, the oil extraction amount is indicated to be an abnormal oil extraction amount, and the terminal can delete the oil extraction amount from the oil extraction amount-oil extraction time sequence.

Correspondingly, the technician can also set a second water injection threshold and a second oil recovery threshold on the terminal, the second water injection threshold being the minimum water injection amount for injecting water into the water injection well, and the second oil recovery threshold being the maximum oil recovery amount for recovering oil from the oil recovery well. When any water injection amount smaller than the second water injection amount threshold value exists in the water injection amount-water injection time series, the water injection amount is indicated as an abnormal water injection amount, and the terminal can delete the water injection amount from the water injection amount-water injection time series. When any oil recovery amount smaller than the second oil recovery threshold exists in the oil recovery amount-oil recovery time sequence, the oil recovery amount is indicated to be an abnormal oil recovery amount, and the terminal can delete the oil recovery amount from the oil recovery amount-oil recovery time sequence.

It should be noted that, the above description is made by taking an example in which the terminal deletes an excessively large or excessively small water injection amount and oil production amount in the water injection amount-water injection time series and the oil production amount-oil production time series of the oil production well, and in other possible embodiments, the terminal may also delete abnormal values in the water injection amount-water injection time series of the water injection well and the oil production amount-oil production time series of the oil production well by preprocessing the water injection amount-water injection time series and the oil production amount-oil production time series of the oil production well in other manners, which is not limited in the examples of the present application.

203. And the terminal inputs the water injection amount-water injection time sequence of the water injection well and the permeability of each water injection layer in the water injection well into a water injection amount splitting model, and the water injection amount-water injection time sequence of each water injection layer is output by the water injection amount splitting model, wherein the water injection amount splitting model is obtained by training according to the water injection amount-water injection time sequence of at least one sample water injection well, the sample water injection amount-water injection time sequence of each sample water injection layer in at least one sample water injection well and the sample permeability.

The training process of the water injection split model refers to the previous description, and is not described herein again.

In a possible implementation manner, the terminal inputs the water injection amount-water injection time sequence of the water injection well and the permeability of each water injection layer in the water injection well into the water injection amount splitting model, and obtains a first seepage range of each water injection layer based on the permeability of each water injection layer through the water injection amount splitting model, wherein the first seepage range is a ratio of the permeability of each water injection layer to the highest permeability of each water injection layer. And the terminal obtains the water injection distribution proportion of each water injection layer based on the permeability of each water injection layer and the seepage range of each water injection layer through a water injection amount splitting model. And the terminal obtains the water injection quantity-water injection time sequence of each water injection layer based on the water injection distribution proportion and the water injection quantity-water injection time sequence of the water injection well.

For example, if the water injection rate-time sequence of a water injection well is (100, 80, 90, 105, 95), the water injection well includes three water injection layers with respective permeabilities of 500 millidarcy (md), 400md, and 600 md. After the terminal inputs the water injection amount-water injection time sequence as (100, 80, 90, 105, 95) into the water injection amount splitting model, the first seepage differences of the three water injection layers, that is, 500/600-0.83, 400/600-0.66 and 600/600-1, are obtained based on the permeability of the three water injection layers by the water injection amount splitting model. Taking the water injection amount splitting model as a Linear Regression (Linear Regression) model as an example, the terminal can splice the permeability (500, 400, 600) of the three water injection layers and the first seepage range (0.83, 0.66, 1) of the three water injection layers to obtain a two-dimensional vector

The terminal carries out two-dimensional vector pair on the basis of the weight matrix and the bias coefficient of the linear regression model

And (3) treating to obtain the water injection distribution ratio of the three water injection layers, such as 0.3: 0.2: 0.5. the terminal can be based on a water injection distribution ratio of 0.3: 0.2: 0.5, the water injection amount-water injection time sequence of the water injection well is treated as (100, 80, 90, 105, 95), and water injection amount-water injection time sequences (30, 24, 27, 31.5, 28.5), (20, 16, 18, 21, 19) and (50, 40, 45, 52.5, 47.5) corresponding to the three water injection zones are obtained.

It should be noted that, the above is described by taking the water injection amount splitting model as a linear regression model as an example, and in other possible embodiments, the water injection amount splitting model may also be a model with other structures, which is not limited in the embodiment of the present application.

In a possible implementation manner, if the terminal trains a plurality of water injection quantity splitting models with different structures, the terminal can input the water injection quantity-water injection time sequence of the water injection well and the permeability of each water injection layer in the water injection well into each water injection quantity splitting model, and each water injection quantity-water injection time sequence of each water injection layer is output by each water injection quantity splitting model. And the terminal performs weighted summation on the water injection quantity-water injection time sequence of each water injection layer output by each water injection quantity splitting model to obtain the water injection quantity-water injection time sequence of each water injection layer.

For example, if the terminal trains two water injection splitting models with different structures, wherein one water injection splitting model is a Classification and Regression tree (Classification and Regression Trees) model, and the other water injection splitting model is a Random Forest (Random Forest) model, the terminal can perform weighted summation on the water injection quantity-water injection time sequences of each water injection layer respectively output by the Classification and Regression tree model and the Random Forest model to obtain the water injection quantity-water injection time sequences of each water injection layer. In some embodiments, the weight of the weighted summation is related to the water injection amount splitting effect of the model during the model test, that is, in the model test process, the model with better water injection amount splitting effect has higher corresponding weight, and the model with worse water injection amount splitting effect has lower corresponding weight. Of course, technicians can also dynamically adjust the weighting of the weighted summation through the terminal according to actual conditions so as to improve the accuracy of the water injection quantity-water injection time sequence of each water injection layer.

For example, if the water injection amount-water injection time sequence of one water injection layer output by the water injection amount splitting model of the classification and regression tree is (30, 24, 27, 32, 30), the water injection amount-water injection time sequence of the same water injection layer output by the water injection amount splitting model of the random forest is (25, 20, 29, 30, 32), the average similarity between the water injection amount-water injection time sequence output by the water injection amount splitting model of the classification and regression tree and the real water injection amount-water injection time sequence is 0.85, the average similarity between the water injection amount-water injection time sequence output by the water injection amount splitting model of the random forest and the real water injection amount-water injection time sequence is 0.70 in the model test process, the terminal can determine that the weight corresponding to the water injection amount splitting model of the classification and regression tree is 0.85/(0.85+0.7) to 0.55, the water injection amount splitting model with the structure of the random forest has the corresponding weight of 1-0.55-0.45. The terminal performs weighted summation on the water filling amount-water filling time sequence (30, 24, 27, 32, 30) and the water filling amount-water filling time sequence (25, 20, 29, 30, 32) based on two weights to obtain (27.8, 22.2, 27.9, 31.1, 30.6).

204. And the terminal inputs the oil extraction amount-oil extraction time sequence of the oil extraction well and the permeability of each oil extraction layer in the oil extraction well into an oil extraction amount splitting model, and the oil extraction amount-oil extraction time sequence of each oil extraction layer is output by the oil extraction amount splitting model, wherein the oil extraction amount splitting model is obtained by training according to the oil extraction amount-oil extraction time sequence of at least one sample oil extraction well, the sample oil extraction amount-oil extraction time sequence of each sample oil extraction layer in at least one sample oil extraction well and the sample permeability.

The training process of the oil recovery split model refers to the previous description, and is not described herein again.

In a possible implementation manner, the terminal inputs the oil production-oil production time sequence of the oil production well and the permeability of each oil production layer in the oil production well into the oil production split model, and obtains the second seepage range of each oil production layer based on the permeability of each oil production layer through the oil production split model, wherein the second seepage range is the ratio of the permeability of each oil production layer to the highest permeability of each oil production layer. And the terminal obtains the oil output proportion of each oil production layer based on the permeability of each oil production layer and the seepage pole difference of each oil production layer through an oil production split model. And the terminal obtains the oil recovery amount-oil recovery time sequence of each oil recovery layer based on the oil yield proportion and the oil recovery amount-oil recovery time sequence of the oil recovery well.

For example, if the oil recovery-time recovery sequence of a production well is (90, 70, 80, 100, 90), the production well includes three production zones, and the three production zones have permeabilities of 600md, 450md, and 800md, respectively. After the terminal inputs the oil recovery amount-oil recovery time sequence as (90, 70, 80, 100, 90) into the oil recovery amount splitting model, the terminal passes through the oil recovery amount splitting model and is based on the penetration of three oil recovery layersThe second seepage rate for the three oil recovery layers was very poor, i.e., 600/800-0.75, 450/800-0.56, and 800/800-1. Taking the oil recovery splitting model as a Linear Regression (Linear Regression) model as an example, the terminal can splice the permeability (600, 450, 800) of three oil production layers and the second seepage range (0.75, 0.56, 1) of the three oil production layers to obtain a two-dimensional vector

Processing is carried out to obtain oil recovery distribution proportions of three oil production layers, such as 0.3: 0.25: 0.45. the terminal can distribute the proportion of 0.3: 0.25: 0.45, the oil recovery-oil recovery time series of the oil recovery well is processed to (90, 70, 80, 100, 90), and oil recovery-oil recovery time series (27, 21, 24, 30, 27), (22.5, 17.5, 20, 25, 22.5) and (40.5, 31.5, 36, 45, 40.5) corresponding to the three oil recovery layers are obtained.

It should be noted that, the above is described by taking the oil recovery split model as a linear regression model as an example, in other possible embodiments, the oil recovery split model may also be a model with other structures, and this is not limited in the embodiment of the present application.

In a possible implementation manner, if the terminal trains a plurality of oil recovery split models with different structures, the terminal can input the oil recovery-oil recovery time series of the oil recovery well and the permeability of each oil recovery layer in the oil recovery well into each oil recovery split model, and each oil recovery split model respectively outputs the oil recovery-oil recovery time series of each oil recovery layer. And the terminal performs weighted summation on the oil recovery-oil recovery time sequence of each oil production layer output by each oil recovery split model to obtain the oil recovery-oil recovery time sequence of each oil production layer.

For example, if the terminal trains two oil recovery splitting models with different structures, one of the oil recovery splitting models is a Classification and Regression tree (Classification and Regression Trees) model, and the other oil recovery splitting model is a Random Forest (Random Forest) model, the terminal can perform weighted summation on the oil recovery-oil recovery time sequences of each oil recovery layer respectively output by the Classification and Regression tree model and the Random Forest model to obtain the oil recovery-oil recovery time sequence of each oil recovery layer. In some embodiments, the weight of the weighted summation is related to the oil recovery split effect of the model during the model test, that is, in the model test process, the model with better oil recovery split effect has higher corresponding weight, and the model with worse oil recovery split effect has lower corresponding weight. Of course, technicians can also dynamically adjust the weighting of the weighted summation through the terminal according to actual conditions so as to improve the accuracy of the oil production-oil production time sequence of each oil production layer.

For example, if the oil recovery-time series of a production zone output by the metric split model with the structure of classification and regression tree is (27, 21, 24, 30, 27), the oil recovery-time series of the same production zone output by the metric split model with the structure of random forest is (25, 18, 26, 28, 33), the average similarity between the oil recovery-time series output by the metric split model with the structure of classification and regression tree and the real oil recovery-time series is 0.75, the average similarity between the oil recovery-time series output by the metric split model with the structure of random forest and the real oil recovery-time series is 0.70 during the model test, the terminal can determine that the weight corresponding to the metric split model with the structure of classification and regression tree is 0.75/(0.75+0.7) × 0.52, the weight corresponding to the oil recovery split model with the structure of random forest is 1-0.52-0.48. The terminal performs weighted summation of the oil recovery-oil recovery time series (27, 21, 24, 30, 27) and the oil recovery-oil recovery time series (25, 18, 26, 28, 33) based on two weights to obtain (26, 19.5, 25, 29, 30).

In addition, after step 203, the terminal can also train the water injection amount splitting model and the oil production amount splitting model based on the data acquired in the production process, that is, the model parameters of the water injection amount splitting model and the oil production amount splitting model are updated in real time in the use process, so that a better water injection amount splitting effect and an oil production amount splitting effect are achieved.

205. And the terminal inputs the water injection amount-water injection time sequence of each water injection layer and the oil recovery amount-oil recovery time sequence of each oil production layer into a correlation determination model, and outputs a correlation coefficient between the water injection amount-water injection time sequence of each water injection layer and the oil recovery amount-oil recovery time sequence of each oil production layer through the correlation determination model.

In a possible implementation mode, the terminal inputs the water injection amount-water injection time sequence of each water injection layer and the oil recovery amount-oil recovery time sequence of each oil production layer into a correlation determination model, and obtains a water injection amount-oil recovery amount difference matrix between each water injection layer and each oil production layer through the correlation determination model, wherein the numerical value in the water injection amount-oil recovery amount difference matrix is the difference value between the water injection amount of each water injection layer and the oil recovery amount of each oil production layer. And the terminal obtains a correlation coefficient between the water injection quantity-water injection time sequence of each water injection layer and the oil recovery quantity-oil recovery time sequence of each oil recovery layer through a correlation determination model based on the water injection quantity-oil recovery quantity difference matrix.

For example, the terminal inputs a water injection amount-water injection time sequence of a water injection layer and an oil production amount-oil production time sequence of an oil production layer into the correlation determination model at one time, and obtains a water injection amount-oil production amount difference matrix between the water injection layer and the oil production layer through the correlation determination model. And the terminal obtains a target path with the upper left corner of the water injection quantity-oil production quantity difference matrix as a starting point and the lower right corner of the water injection quantity-oil production quantity difference matrix as an end point through the correlation determination model, wherein the target path is the path with the minimum sum of the passed numerical values. And the terminal determines the sum of the numerical values passed by the target path as a correlation coefficient, and the magnitude of the correlation coefficient is in inverse proportion to the similarity between the water injection quantity-water injection time sequence and the oil production quantity-oil production time sequence.

For example, the water injection amount-water injection time series of the water injection zone is a (20, 16, 18, 21, 19), the oil recovery amount-oil recovery time series of the oil recovery zone is B (27, 21, 24, 30, 27), and the terminal obtains the correlation determination modelTaking a difference matrix of water injection quantity and oil production quantity between the water injection layer and the oil production layer

Each value in the water injection-oil recovery difference matrix is a difference between one value in the water injection-water injection time series a (20, 16, 18, 21, 19) and another value in the oil recovery-oil recovery time series B (27, 21, 24, 30, 27). For example, for the first number "7" in the upper left corner of the water injection-oil production difference matrix, it is the difference between the first value "27" in the oil production-oil production time series B (27, 21, 24, 30, 27) and the first value "20" in the water injection-water injection time series a (20, 16, 18, 21, 19). For the second number "11" in the upper left corner of the water injection-oil production difference matrix, this is the difference between the first number "27" in the oil production-oil production time series B (27, 21, 24, 30, 27) and the second number "16" in the water injection-water injection time series a (20, 16, 18, 21, 19), and so on.

The process of starting from the first value "7" at the upper left corner of the water injection-oil recovery difference matrix and reaching the last value "8" at the lower right corner of the water injection-oil recovery difference matrix is explained below. In order to ensure that the target path is the path with the minimum sum of the passed numerical values, the terminal can compare the size of each number on the advancing path in real time, and the minimum numerical value is passed when each step of advancing is ensured. Starting from "7", the next step of "7" has three values "1", "11" and "5", and the terminal determines that "1" is the smallest value of the three values, and then takes the value "1" as the forward position. The terminal continues to start from the value "1", compares the magnitudes of three values "4", "8" and "5" in front of the value "1", determines "4" as the smallest value of the three values, and then takes the value "4" as the forward position. After multiple comparisons and advances, the terminal can obtain that the target path is 7+1+4+8+6+3+5+11+ 8', the length of the target path is 53, and the length of the target path is also the correlation coefficient between the water injection layer and the oil production layer.

It should be noted that, the above description process takes an example of obtaining a correlation coefficient between one water injection layer and one oil production layer by a terminal as an example, and a method for obtaining correlation coefficients between multiple water injection layers and multiple oil production layers by a terminal belongs to the same inventive concept as the above process, and is not described herein again.

206. And the terminal determines the injection-production communication strength between each water injection layer and each oil production layer based on the correlation coefficient.

In a possible implementation mode, the terminal performs normalization processing on the correlation coefficient, and determines the injection-production communication strength between each water injection layer and each oil production layer. Optionally, the method used by the terminal to normalize the correlation coefficient is soft maximization (Softmax) or S-shaped growth curve (Sigmoid), which is not limited in this embodiment of the present application.

Taking a water injection layer as an example, the terminal obtains the correlation coefficients between the water injection layer and three oil production layers respectively as 53, 27 and 20 through a correlation determination model. The terminal can then use the Softmax pair (53, 27,20) for normalization (0.53,0.27, 0.2). The terminal can obtain the reciprocal (1/0.53,1/0.27,1/0.2) of the normalized correlation coefficient, and the reciprocal (1/0.53,1/0.27,1/0.2) is used as the injection-production communication strength between the water injection layer and the three oil production layers, wherein the larger the numerical value of the injection-production communication strength is, the better the connectivity between the water injection layer and the oil production layers is identified.

It should be noted that, the steps 201-206 are described by taking a terminal as an execution subject as an example, in other possible embodiments, the steps 201-206 can also be executed by taking a server as an execution subject, and the embodiment of the present application is not limited to the type of the execution subject.

Fig. 3 is a schematic structural diagram of an injection-production communication strength determining apparatus according to an embodiment of the present application, and referring to fig. 3, the apparatus includes: the system comprises an acquisition module 301, a first input module 302, a second input module 303, a third input module 304 and an injection-production communication strength determination module 305.

The acquiring module 301 is configured to acquire a water injection amount-water injection time sequence of the water injection well and an oil recovery amount-oil recovery time sequence of the oil recovery well.

The first input module 302 is configured to input the water injection amount-water injection time series of the water injection well and the permeability of each water injection layer in the water injection well into the water injection amount splitting model, and output the water injection amount-water injection time series of each water injection layer by the water injection amount splitting model, where the water injection amount splitting model is obtained by training the water injection amount-water injection time series of at least one sample water injection well, the sample water injection amount-water injection time series of each sample water injection layer in at least one sample water injection well, and the sample permeability.

And a second input module 303, configured to input the oil recovery amount-oil recovery time series of the oil recovery well and the permeability of each oil recovery layer in the oil recovery well into the oil recovery amount splitting model, and output the oil recovery amount-oil recovery time series of each oil recovery layer by the oil recovery amount splitting model, where the oil recovery amount splitting model is obtained by training according to the oil recovery amount-oil recovery time series of at least one sample oil recovery well, and the sample oil recovery amount-oil recovery time series and the sample permeability of each sample oil recovery layer in at least one sample oil recovery well.

And a third input module 304, configured to input the water injection amount-water injection time series of each water injection layer and the oil recovery amount-oil recovery time series of each oil recovery layer into the correlation determination model, and output a correlation coefficient between the water injection amount-water injection time series of each water injection layer and the oil recovery amount-oil recovery time series of each oil recovery layer through the correlation determination model.

And an injection-production communication strength determining module 305, configured to determine injection-production communication strength between each water injection layer and each oil production layer based on the correlation coefficient.

In a possible embodiment, the first input module is configured to input the water injection amount-water injection time series of the water injection well and the permeability of each water injection layer in the water injection well into the water injection amount splitting model, and obtain, through the water injection amount splitting model, a first seepage range of each water injection layer based on the permeability of each water injection layer, where the first seepage range is a ratio between the permeability of each water injection layer and the highest permeability of each water injection layer. And obtaining the water injection distribution proportion of each water injection layer based on the permeability of each water injection layer and the seepage range of each water injection layer through a water injection amount splitting model. And obtaining the water injection quantity-water injection time sequence of each water injection layer based on the water injection distribution proportion and the water injection quantity-water injection time sequence of the water injection well.

In a possible embodiment, the second input module is configured to input the oil recovery-oil recovery time series of the oil recovery well and the permeability of each oil recovery layer in the oil recovery well into the oil recovery split model, and obtain the second seepage range of each oil recovery layer through the oil recovery split model based on the permeability of each oil recovery layer, where the second seepage range is a ratio between the permeability of each oil recovery layer and the highest permeability of each oil recovery layer. And obtaining the oil output proportion of each oil production layer based on the permeability of each oil production layer and the seepage pole difference of each oil production layer through an oil production split model. And obtaining the oil recovery amount-oil recovery time sequence of each oil recovery layer based on the oil yield proportion and the oil recovery amount-oil recovery time sequence of the oil recovery well.

In a possible implementation manner, the third input module is configured to input the water injection amount-water injection time series of each water injection layer and the oil recovery amount-oil recovery time series of each oil recovery layer into the correlation determination model, and obtain a water injection amount-oil recovery amount difference matrix between each water injection layer and each oil recovery layer through the correlation determination model, where a numerical value in the water injection amount-oil recovery amount difference matrix is a difference between the water injection amount of each water injection layer and the oil recovery amount of each oil recovery layer. And obtaining a correlation coefficient between the water injection quantity-water injection time sequence of each water injection layer and the oil recovery quantity-oil recovery time sequence of each oil recovery layer through a correlation determination model based on the water injection quantity-oil recovery quantity difference matrix.

In a possible implementation manner, the third input module is configured to obtain, through the correlation determination model, a target path with a starting point at the upper left corner of the water injection amount-oil production amount difference matrix and an ending point at the lower right corner of the water injection amount-oil production amount difference matrix, where the target path is a path with the smallest sum of the passed values. And determining the sum of the values passed by the target path as a correlation coefficient.

It should be noted that: the injection-production communication strength determining apparatus provided in the above embodiment is only illustrated by dividing the functional modules when determining the injection-production communication strength, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the injection-production communication strength determination apparatus and the injection-production communication strength determination method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiments and are not described herein again.

In the embodiment of the present application, the electronic device may be implemented as a terminal or a server, and a structure of the terminal is described below.

Fig. 4 shows a block diagram of a terminal 400 according to an exemplary embodiment of the present application. The terminal 400 may be a portable mobile terminal such as: a smartphone, a tablet, a laptop, or a desktop computer. The terminal 400 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

Generally, the terminal 400 includes: a processor 401 and a memory 402.

Processor 401 may include one or more processing cores, such as a 4-core processor, an 8-core processor, or the like. The processor 401 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 401 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 401 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content that the display screen needs to display. In some embodiments, the processor 401 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 402 may include one or more computer-readable storage media, which may be non-transitory. Memory 402 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 402 is used to store at least one program code for execution by processor 401 to implement the method of voidage replacement connectivity determination provided by method embodiments herein.

In some embodiments, the terminal 400 may further optionally include: a peripheral interface 403 and at least one peripheral. The processor 401, memory 402 and peripheral interface 403 may be connected by bus or signal lines. Each peripheral may be connected to the peripheral interface 403 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 404, a display screen 405, a camera assembly 406, an audio circuit 407, a positioning assembly 408, and a power supply 409.

The peripheral interface 403 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 401 and the memory 402. In some embodiments, processor 401, memory 402, and peripheral interface 403 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 401, the memory 402 and the peripheral interface 403 may be implemented on a separate chip or circuit board, which is not limited by this embodiment.

The Radio Frequency circuit 404 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 404 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 404 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 404 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuitry 404 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: the world wide web, metropolitan area networks, intranets, generations of mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the rf circuit 404 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 405 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 405 is a touch display screen, the display screen 405 also has the ability to capture touch signals on or over the surface of the display screen 405. The touch signal may be input to the processor 401 as a control signal for processing. At this point, the display screen 405 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display screen 405 may be one, disposed on the front panel of the terminal 400; in other embodiments, the display screen 405 may be at least two, respectively disposed on different surfaces of the terminal 400 or in a folded design; in other embodiments, the display 405 may be a flexible display disposed on a curved surface or a folded surface of the terminal 400. Even further, the display screen 405 may be arranged in a non-rectangular irregular pattern, i.e. a shaped screen. The Display screen 405 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and other materials.

The camera assembly 406 is used to capture images or video. Optionally, camera assembly 406 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 406 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

The audio circuit 407 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 401 for processing, or inputting the electric signals to the radio frequency circuit 404 for realizing voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the terminal 400. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 401 or the radio frequency circuit 404 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, audio circuitry 407 may also include a headphone jack.

The positioning component 408 is used to locate the current geographic position of the terminal 400 for navigation or LBS (Location Based Service). The Positioning component 408 can be a Positioning component based on the Global Positioning System (GPS) in the united states, the beidou System in china, or the galileo System in russia.

The power supply 409 is used to supply power to the various components in the terminal 400. The power source 409 may be alternating current, direct current, disposable or rechargeable. When the power source 409 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. The wired rechargeable battery is a battery charged through a wired line, and the wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, the terminal 400 also includes one or more sensors 410. The one or more sensors 410 include, but are not limited to: acceleration sensor 411, gyro sensor 412, pressure sensor 413, fingerprint sensor 414, optical sensor 415, and proximity sensor 416.

The acceleration sensor 411 may detect the magnitude of acceleration in three coordinate axes of the coordinate system established with the terminal 400. For example, the acceleration sensor 411 may be used to detect components of the gravitational acceleration in three coordinate axes. The processor 401 may control the display screen 405 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 411. The acceleration sensor 411 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 412 may detect a body direction and a rotation angle of the terminal 400, and the gyro sensor 412 may cooperate with the acceleration sensor 411 to acquire a 3D motion of the terminal 400 by the user. From the data collected by the gyro sensor 412, the processor 401 may implement the following functions: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.

The pressure sensor 413 may be disposed on a side bezel of the terminal 400 and/or on a lower layer of the display screen 405. When the pressure sensor 413 is disposed on the side frame of the terminal 400, a user's holding signal to the terminal 400 can be detected, and the processor 401 performs left-right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 413. When the pressure sensor 413 is disposed at the lower layer of the display screen 405, the processor 401 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 405. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 414 is used for collecting a fingerprint of the user, and the processor 401 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 414, or the fingerprint sensor 414 identifies the identity of the user according to the collected fingerprint. Upon recognizing that the user's identity is a trusted identity, processor 401 authorizes the user to perform relevant sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings, etc. The fingerprint sensor 414 may be disposed on the front, back, or side of the terminal 400. When a physical key or vendor Logo is provided on the terminal 400, the fingerprint sensor 414 may be integrated with the physical key or vendor Logo.

The optical sensor 415 is used to collect the ambient light intensity. In one embodiment, processor 401 may control the display brightness of display screen 405 based on the ambient light intensity collected by optical sensor 415. Specifically, when the ambient light intensity is high, the display brightness of the display screen 405 is increased; when the ambient light intensity is low, the display brightness of the display screen 405 is reduced. In another embodiment, the processor 401 may also dynamically adjust the shooting parameters of the camera assembly 406 according to the ambient light intensity collected by the optical sensor 415.

A proximity sensor 416, also known as a distance sensor, is typically disposed on the front panel of the terminal 400. The proximity sensor 416 is used to collect the distance between the user and the front surface of the terminal 400. In one embodiment, when the proximity sensor 416 detects that the distance between the user and the front surface of the terminal 400 gradually decreases, the processor 401 controls the display screen 405 to switch from the bright screen state to the dark screen state; when the proximity sensor 416 detects that the distance between the user and the front surface of the terminal 400 is gradually increased, the processor 401 controls the display screen 405 to switch from the breath-screen state to the bright-screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 4 is not intended to be limiting of terminal 400 and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components may be used.

Fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors 501 and one or more memories 502, where the one or more memories 502 store at least one program code, and the at least one program code is loaded and executed by the one or more processors 501 to implement the methods provided by the foregoing method embodiments. Of course, the server 500 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 500 may also include other components for implementing the functions of the device, which is not described herein again.

In an exemplary embodiment, a computer readable storage medium, such as a memory including program code, executable by a processor, is also provided to perform the method of voidage replacement connectivity determination in the above embodiments. For example, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by hardware associated with program code, and the program may be stored in a computer readable storage medium, where the above mentioned storage medium may be a read-only memory, a magnetic or optical disk, etc.

The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. An injection-production communication strength determination method, characterized by comprising:

2. The method of claim 1, wherein inputting the water injection amount-water injection time series of the water injection well and the permeability of each water injection layer in the water injection well into a water injection amount splitting model, and outputting the water injection amount-water injection time series of each water injection layer by the water injection amount splitting model comprises:

3. The method of claim 1, wherein inputting the oil recovery-oil recovery time series for the oil recovery well and the permeability of each oil recovery zone in the oil recovery well into a yield split model, outputting the oil recovery-oil recovery time series for each oil recovery zone by the yield split model comprises:

4. The method of claim 1, wherein inputting the water injection amount-water injection time series of each water injection layer and the oil production amount-oil production time series of each oil production layer into a correlation determination model, and outputting correlation coefficients between the water injection amount-water injection time series of each water injection layer and the oil production amount-oil production time series of each oil production layer through the correlation determination model comprises:

5. The method of claim 4, wherein the obtaining, by the correlation determination model, correlation coefficients between the water injection-water injection time series of the respective water injection zones and the oil production-oil production time series of the respective oil production zones based on the water injection-oil production difference matrix comprises:

6. The method of claim 1, wherein the determining an injection-production communication strength between the respective water injection layer and the respective oil production layer based on the correlation coefficient comprises:

7. The method of claim 1, wherein a distance between the water injection well and the production well is less than or equal to a distance threshold.

8. An injection-production communication strength determination apparatus, characterized by comprising:

9. A computer device comprising one or more processors and one or more memories having at least one program code stored therein, the program code being loaded and executed by the one or more processors to implement the voidage replacement connectivity strength determining method of any one of claims 1 to 7.

10. A computer-readable storage medium having at least one program code stored therein, the program code being loaded and executed by a processor to implement the method of determining voidage replacement (egl) according to any one of claims 1 to 7.